{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:18:13Z","timestamp":1771514293750,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322318"],"award-info":[{"award-number":["62322318"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ANR\/RGC Joint Research Scheme of the Research Grants Council of the Hong Kong Special Administrative Region, China"},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["A-CUHK402\/23"],"award-info":[{"award-number":["A-CUHK402\/23"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science, Technology and Innovation Commission of Shenzhen Municipality","award":["SGDX20220530111201008"],"award-info":[{"award-number":["SGDX20220530111201008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/jbhi.2025.3532311","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T18:43:01Z","timestamp":1739472181000},"page":"3526-3536","source":"Crossref","is-referenced-by-count":4,"title":["Improving Foundation Model for Endoscopy Video Analysis via Representation Learning on Long Sequences"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1860-8391","authenticated-orcid":false,"given":"Zhao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1478-3232","authenticated-orcid":false,"given":"Lingting","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong"}]},{"given":"Tongtong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8719-448X","authenticated-orcid":false,"given":"Shaoting","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3416-9950","authenticated-orcid":false,"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_55"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3277029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-018-1772-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3381517"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3177077"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3063716"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103366"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref11","first-page":"1","article-title":"BEit: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref13","first-page":"1","article-title":"Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-02102-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32254-0_49"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255809"},{"key":"ref19","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2787657"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2547947"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2020.07.060"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1371-y"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref31","first-page":"28541","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref32","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":""},{"key":"ref33","article-title":"Grounded knowledge-enhanced medical VLP for chest X-ray","author":"Deng","year":"2024","journal-title":""},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref36","article-title":"Customvideo: Customizing text-to-video generation with multiple subjects","author":"Wang","year":"2024","journal-title":""},{"key":"ref37","first-page":"22226","article-title":"One-2-3-45: Any single image to 3D mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref38","article-title":"Generative enhancement for 3D medical images","author":"Zhu","year":"2024","journal-title":""},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref49","first-page":"1","article-title":"Layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Deep Learn. Symp.","author":"Ba","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00622-y"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00920-z"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"key":"ref54","first-page":"1","article-title":"Spreading vectors for similarity search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sablayrolles","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00784"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_9"},{"key":"ref60","first-page":"26462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref61","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref62","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref63","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_29"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-77610-6_13"},{"key":"ref67","first-page":"135","article-title":"Hfgs: 4D Gaussian splatting with emphasis on spatial and temporal high-frequency components for endoscopic scene reconstruction","volume-title":"Proc. 35th Brit. Mach. Vis. Conf.","author":"Zhao","year":"2024"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/10989059\/10885043.pdf?arnumber=10885043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T17:54:27Z","timestamp":1746640467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10885043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":67,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3532311","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}